wehub-resource-sync
42 lines
962 B
Python
42 lines
962 B
Python
"""
|
|
Basic example of scraping pipeline using SmartScraper
|
|
"""
|
|
|
|
import json
|
|
import os
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
from scrapegraphai.graphs import SmartScraperMultiGraph
|
|
|
|
load_dotenv()
|
|
|
|
# ************************************************
|
|
# Define the configuration for the graph
|
|
# ************************************************
|
|
|
|
openai_key = os.getenv("OPENAI_APIKEY")
|
|
|
|
graph_config = {
|
|
"llm": {
|
|
"api_key": openai_key,
|
|
"model": "openai/gpt-4o",
|
|
},
|
|
"verbose": True,
|
|
"headless": False,
|
|
}
|
|
|
|
# *******************************************************
|
|
# Create the SmartScraperMultiGraph instance and run it
|
|
# *******************************************************
|
|
|
|
multiple_search_graph = SmartScraperMultiGraph(
|
|
prompt="Who is ?",
|
|
source=["https://perinim.github.io/", "https://perinim.github.io/cv/"],
|
|
schema=None,
|
|
config=graph_config,
|
|
)
|
|
|
|
result = multiple_search_graph.run()
|
|
print(json.dumps(result, indent=4))
|